Trending Research
STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model
In this work, we introduce Spatial-Temporal Graph Mamba (STG-Mamba) as the first exploration of leveraging the powerful selective state space models for STG learning by treating STG Network as a system, and employing the Graph Selective State Space Block (GS3B) to precisely characterize the dynamic evolution of STG networks.
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Mode
Heuristics are indispensable for tackling complex search and optimization problems.
Generative Agents: Interactive Simulacra of Human Behavior
Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools.
AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation
We propose AutoCrawler, a two-stage framework that leverages the hierarchical structure of HTML for progressive understanding.
MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation
bytedance/MoMA
•
•
This approach effectively synergizes reference image and text prompt information to produce valuable image features, facilitating an image diffusion model.
FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering
To investigate these aspects, we create and publish a novel TQA evaluation benchmark in English.
MMBench: Is Your Multi-modal Model an All-around Player?
In response to these challenges, we propose MMBench, a novel multi-modality benchmark.
Ranked #1 on
Visual Question Answering
on MMBench
ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations
Here we propose SAPIEN Manipulation Skill Benchmark (ManiSkill) to benchmark manipulation skills over diverse objects in a full-physics simulator.
NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment
However, building efficient tools to perform alignment can be challenging, especially for the largest and most competent LLMs which often contain tens or hundreds of billions of parameters.
Learning to correct spectral methods for simulating turbulent flows
google/jax-cfd
•
•
We build upon Fourier-based spectral methods, which are known to be more efficient than other numerical schemes for simulating PDEs with smooth and periodic solutions.
